Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition

By Noriko Takemura, Yasushi Makihara, Daigo Muramatsu, Tomio Echigo, Yasushi Yagi. IPSJ Transactions on Computer Vision and Applications, 2018

458 citations recorded by the source corpus.

This paper describes the world’s largest gait database with wide view variation, the “OU-ISIR gait database, multi-view large population dataset (OU-MVLP)”, and its application to a statistically reliable performance evaluation of vision-based cross-view gait recognition. Specifically, we construct a gait dataset that includes 10,307 subjects (5114 males and 5193 females) from 14 view angles ranging 0° −90°, 180° −270°.In addition, we evaluate various approaches to gait recognition which are robust against view angles. By using our dataset, we can fully exploit a state-of-the-art method requiring a large number of training samples, e.g., CNN-based cross-view gait recognition method, and we validate effectiveness of such a family of the methods.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Endocrinology, Diabetes and Metabolism

View Paper: https://www.semanticscholar.org/paper/cd4e1e3454d1beb3ea63ae0544927d675220db68

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Yongzhen Huang
2. Gerhard Rigoll
3. Xin Yu
4. Beibei Lin
5. Shunli Zhang
6. Torben Teepe
7. Johannes Gilg
8. Fabian Herzog

In Computer Vision and Pattern Recognition

1. Xin Yu
2. Yongzhen Huang
3. Gerhard Rigoll
4. Yunjie Peng
5. Chao Fan
6. Beibei Lin
7. Shunli Zhang
8. Torben Teepe

Citations in the corpus

• GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition (2018, methodology): “The silhou-ettes are directly provided by the datasets and are aligned based on methods in (Takemura et al. 2018b).”
• GaitPart: Temporal Part-Based Model for Gait Recognition (2020, methodology): “In order to verify its generalization, the evaluation of GaitPart is completed on the worldwide largest public gait dataset[21].”
• Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation (2020, background): “The OUMVLP dataset [19] is one of the largest gait recognition databases, which contains 10,307 subjects in total.”
• Gaitgraph: Graph Convolutional Network for Skeleton-Based Gait Recognition (2021, methodology): “Therefore we cannot evaluate on the largest public gait dataset OU-MVLP [20], the evaluation on the commonly used dataset CASIA-B provides a comparison with other methods.”